"OpenRouter thinking or reasoning capabilities" matching MCP servers:

A Model Context Protocol server that enhances Claude in Cursor AI with advanced reasoning capabilities including Monte Carlo Tree Search, Beam Search, R1 Transformer, and Hybrid Reasoning methods.

An intelligent, agentic MCP server gateway to OpenRouter's 200+ AI models. It provides budget controls, security features, semantic memory, and code search capabilities.

Enables structured, iterative reasoning for complex problem-solving with features like confidence tracking, revision mechanisms, and branching support. Provides flexible validation and multiple output formats for systematic analysis and decision-making tasks.

Enables coding or reasoning agents to request structured judgments from TypeSafe's Jev model at decision points, including choices, scores, claim verification, and code reviews, with probabilities and confidence returned as data.

A codebase-memory MCP server for AI coding agents with hybrid semantic+BM25 code search, structural outlines, a work journal, and gaze-and-think deep reasoning over a local LanceDB database.

An MCP server that indexes reference repositories and provides tools for AI coding agents to retrieve lossless code context, enabling reasoning over codebases larger than the agent's context window.

A read-only MCP server that gives Codex and other clients a Kimi K3 second opinion through OpenRouter, enabling algorithm review, code review, and project planning.

Provides AI agents with powerful JavaScript/TypeScript code analysis and transformation capabilities using the tree-hugger-js library.

MCP server for DeepSeek AI models (Chat + Reasoner). Supports multi-turn sessions, model fallback with circuit breaker, function calling, thinking mode, JSON output, multimodal input, and cost tracking.

An MCP server that lets AI agents review code using language models, supporting git diffs, files, and snippets with severity levels. Works with Ollama (local) and hosted providers like OpenAI, Anthropic, and OpenRouter.

Connects Kimi Code with Claude Code, enabling Claude to delegate bulk codebase reading to Kimi (256K context) for cost savings, while Claude focuses on reasoning and code edits.

Enables consulting oracle AI models (Codex or Claude) for expert reasoning and analysis on complex problems, architectural decisions, and design tradeoffs through a unified CLI interface.

A project-aware AI design and code review server that uses dual reviewers via OpenRouter to catch context-blind errors in AI-generated code, optionally integrating with Serena for long-term project memory.

Generates DeepWiki-style documentation for private code repositories with RAG-based Q\&A capabilities, semantic code search, and multi-language AST parsing. Supports local LLMs (Ollama) or cloud providers for privacy-focused codebase analysis.

An MCP server that enables persistent memory, structured thinking sessions, and project-based knowledge management for Claude. It includes specialized coding tools for package discovery and reinvention prevention by validating code against existing libraries and APIs.

Transforms your local repository into a shared project brain using recursive reasoning and local LLMs to analyze, reason, and remember project architecture.

Enables agents to connect to Language Server Protocol servers as a headless editor, exposing LSP capabilities like diagnostics, rename, and formatting through MCP tools and resources.

Provides unified development tools including code analysis, debugging, refactoring, documentation, testing, and project automation through multiple LLM providers (KIMI, GLM, OpenRouter). Features agentic audit capabilities with multi-model consensus for finding issues and generating direct fixes.

A production-grade MCP server providing advanced code intelligence capabilities such as semantic search, dependency analysis, and natural language Q&A across multiple programming languages.

Enables AI agents to analyze large codebases and document collections by consulting large context window models (up to 2M tokens) via OpenRouter when files exceed the current agent's context limits.